Representing and Solving Decision Problems with Limited Information
提出有限记忆影响图（LIMID）模型，放松了传统决策问题中无遗忘的假设，适用于多决策者或记忆受限场景，并给出通过局部策略更新优化决策的算法。
We introduce the notion of LImited Memory Influence Diagram (LIMID) to describe multistage decision problems in which the traditional assumption of no forgetting is relaxed. This can be relevant in situations with multiple decision makers or when decisions must be prescribed under memory constraints, such as in partially observed Markov decision processes (POMDPs). We give an algorithm for improving any given strategy by local computation of single policy updates and investigate conditions for the resulting strategy to be optimal.